Releases: Evil0ctal/Fast-Powerful-Whisper-AI-Services-API
Releases · Evil0ctal/Fast-Powerful-Whisper-AI-Services-API
V1.0.5
🔊 V1.0.5 Release Notes
[English]
- 🐛 Bug Fix - Resolved compatibility issues with the
TaskPriority
enum when using SQLite as the database. -> #3 - 📄 Documentation Update - Enhanced Swagger UI documentation for task creation, explicitly listing available
TaskPriority
parameters for better user understanding.
⚠️ Upgrade Notes from V1.0.4 to V1.0.5
Due to database structural changes, consider the following options:
- Modify Existing Database: Update the
TaskPriority
enum values in your current database to align with the new format. Refer to the migration guide for detailed instructions. - Start Fresh: Abandon the old database and allow the updated code to create a new blank database. Then, migrate any necessary data manually.
🔊 V1.0.5 更新日志
[中文]
- 🐛 Bug 修复 - 修复了在使用 SQLite 作为数据库时,
TaskPriority
枚举的兼容性问题。-> #3 - 📄 文档更新 - 优化了任务创建的 Swagger UI 文档介绍,明确列出了
TaskPriority
的可用参数,提升用户体验。
⚠️ 从 V1.0.4 升级到 V1.0.5 的注意事项
由于数据库结构发生变更,请注意以下两种升级方案:
- 修改现有数据库:更新现有数据库中
TaskPriority
的枚举值,使其与新版本的格式保持一致。详细的迁移步骤请参考迁移指南。 - 重新创建数据库:放弃旧的数据库,让最新版本的代码自动创建一个新的空白数据库。随后,手动迁移必要的数据。
V1.0.4
🔊 V1.0.4 Release Notes
[English]
- 🔧 Code Structure Optimization - Improved maintainability and execution efficiency.
- 🚀 Added LLM Model Support - Integrated ChatGPT as the model for task analysis.
- 🗃️ Database Structure Refactoring - Restructured the database for easier future expansion.
- 🔍 New Summary Interface - Enables ChatGPT to summarize content based on crawler task input.
- 📄 Documentation Enhancement - Expanded API documentation in Swagger UI for better readability and user experience.
- 🐛 ** Bug Fix** - Fix extra parameters passed when using SQLite as Database #2
🔊 V1.0.4 更新日志
[中文]
- 🔧 代码结构优化 - 提升代码的可维护性和执行效率。
- 🚀 新增LLM模型支持 - 使用ChatGPT作为任务分析的模型支持。
- 🗃️ 数据库结构重构 - 重构数据库结构,便于未来扩展。
- 🔍 新增总结接口 - 将爬虫任务作为输入源让ChatGPT来总结内容。
- 📄 文档优化 - Swagger UI 中的接口文档更加详尽,提升可读性与用户体验。
- 🐛 ** Bug 修复** - 修复在使用SQLite作为数据库时传递的以外参数 #2
V1.0.3
🔊 V1.0.3 Release Notes
[English Version]
- 🔧 Code Structure Optimization - Improved code maintainability and execution efficiency.
- 🚀 New Model Support - Default engine switched to the Faster Whisper model, delivering a significant performance boost.
- 📝 Task Type Options - Directly specify
transcribe
ortranslate
as task types upon creation. - 🌐 Output Language Selection - Choose target languages for task output, with auto-translation support.
- ⚙️ AI Model Pool Enhancement - Enhanced model pool logic with automatic adjustment based on different engines. Now supports both concurrency and singleton modes with multi-GPU compatibility.
- 🗃️ Database Structure Overhaul - Restructured database for improved scalability.
- 💾 New Database Support - Now defaults to SQLite, with an option to switch to MySQL for enhanced performance.
- 🔍 New Query Interface - Provides finer task query granularity, improving accuracy and flexibility.
- 📄 Enhanced Documentation - More detailed API documentation in Swagger UI for better readability and user experience.
- 🌐 Crawler Module Added - Introduced crawlers for TikTok and Douyin with corresponding task support.
🔊 V1.0.3 更新日志
[中文]
- 🔧 代码结构优化 - 提升代码的可维护性和执行效率。
- 🚀 新增模型支持 - 默认引擎切换为 Faster Whisper 模型,性能显著提升。
- 📝 任务类型选项 - 创建任务时可直接指定
transcribe
或translate
类型。 - 🌐 输出语言选择 - 支持选择目标语言,并提供自动翻译功能。
- ⚙️ AI模型池增强 - 模型池逻辑根据不同引擎自动调节,支持并发和单例模式,现支持多 GPU 并发处理。
- 🗃️ 数据库结构重构 - 重构数据库结构,便于未来扩展。
- 💾 新增数据库支持 - 默认使用 SQLite 数据库,同时支持切换至 MySQL 以增强性能。
- 🔍 新增查询接口 - 提供更细粒度的任务查询功能,提高查询的精确性和灵活性。
- 📄 文档优化 - Swagger UI 中的接口文档更加详尽,提升可读性与用户体验。
- 🌐 新增爬虫模块 - 增加对 TikTok 和抖音的爬虫模块及相应的任务支持。
V1.0.2
🔊 V1.0.2 更新日志
[中文]
- 🔧 代码结构优化 - 提升代码的可维护性和执行效率。
- 🚀 新增模型支持 - 默认引擎切换为 Faster Whisper 模型,性能显著提升。
- 📝 任务类型支持 - 在创建任务时,可直接指定
transcribe
或translate
作为任务类型。 - 🌐 输出语言选择 - 创建任务时,可选择输出目标语言,支持自动翻译。
- ⚙️ AI模型池优化 - 模型池逻辑根据不同引擎自动调节,支持并发和单例模式。
- 🗃️ 数据库结构调整 - 重构数据库,便于未来扩展。
- 🔍 新增查询接口 - 提供更细粒度的任务查询功能,提升查询精确度。
- 📄 文档优化 - Swagger UI 中的接口文档更加详尽,提升可读性和用户体验。
🔊 V1.0.2 Changelog
[English]
- 🔧 Code Structure Optimization - Improved maintainability and performance.
- 🚀 New Model Support - Added support for the Faster Whisper model, now set as the default engine.
- 📝 Task Type Options - When creating tasks, users can now specify task types such as
transcribe
ortranslate
. - 🌐 Output Language Selection - Users can set the target output language during task creation to automate translations.
- ⚙️ AI Model Pool Enhancement - The model pool logic now adapts automatically for different engines, supporting both concurrent and singleton modes.
- 🗃️ Database Structure Update - Database restructured to facilitate future expansions.
- 🔍 New Query Interface - Added more granular task query options for improved database search precision.
- 📄 Documentation Improvement - Expanded API documentation in Swagger UI for better readability and user experience.
V1.0.1
🔊 V1.0.1 Changelog
[中文]
- 🔧 优化代码结构 - 提高可维护性和性能。
- 🚀 AI模型池 - 使用异步方式创建了一个AI模型池,实现高效的并发任务处理。
- 📊 任务优先级 - 通过
priority
参数支持不同优先级的任务处理,确保关键任务优先执行。 - 🕸️ 新增爬虫模块 - 准备支持数据爬取与处理,以应对更多应用场景。
- ⚙️ 更新FastAPI生命周期管理 - 使用FastAPI的
lifespan
代替@app.on_event
,更好地支持ASGI 3.0
协议。 - 🗃️ 数据库重构 - 重新设计了数据库结构,为后续扩展奠定基础。
- ⚡ 性能优化 - 利用
asyncio
深度优化性能,开发环境为Python V3.11
,部分低版本可能不再兼容。
[English]
- 🔧 Optimized Code Structure - Improved maintainability and performance.
- 🚀 AI Model Pool - Implemented an asynchronous AI model pool for efficient concurrent task processing.
- 📊 Task Priority - Added support for task priority with the
priority
parameter to ensure critical tasks are processed first. - 🕸️ New Web Scraping Module - Prepared for future support in data scraping and processing to expand application scenarios.
- ⚙️ FastAPI Lifecycle Management Update - Replaced
@app.on_event
with FastAPI’slifespan
for better compliance withASGI 3.0
. - 🗃️ Database Redesign - Redesigned the database structure for future scalability.
- ⚡ Performance Optimization - Leveraged
asyncio
for deep performance enhancements. The development environment is set toPython V3.11
, which may limit compatibility with lower versions.
V1.0.0
[中文]
- ✨ 实现异步任务队列 :高效管理任务执行与处理,提升并发能力,适用于需要快速语音转录和内容分析的应用程序。
- 🧠 封装 Whisper Large-V3 模型 :集成 OpenAI Whisper 模型,实现强大的语音识别功能,特别适合多语言内容处理。
- 🚀 添加 CUDA 支持 :支持 GPU 加速计算,处理速度提升 3 倍以上,同时在 GPU 不可用时自动切换为 CPU,确保持续运行。
- 📂 高性能文件处理类 :优化文件操作性能,轻松处理大文件。
- 💾 高性能数据库类 :支持任务存储及历史记录查询,任务管理更高效。
- 📈 未来改进方向 :即将支持更多格式和新的优化策略。
- 📝 更新自述文档 :增强文档内容,便于用户快速上手,提升用户体验。
[English]
- ✨ Implemented Asynchronous Task Queue : Efficiently manages task execution with improved concurrency, ideal for applications needing fast speech transcription and content analysis.
- 🧠 Integrated Whisper Large-V3 Model : Featuring OpenAI’s Whisper model, providing robust speech recognition, particularly suited for multi-language processing.
- 🚀 Added CUDA Support : Accelerates processing speed by over 3x with GPU support and automatically falls back to CPU, ensuring uninterrupted functionality.
- 📂 High-Performance File Handling Class : Optimized to handle large files smoothly and efficiently.
- 💾 High-Performance Database Class : Supports task storage and historical queries, improving overall task management.
- 📈 Future Improvements : More format support and new optimization strategies planned for upcoming releases.
- 📝 Updated Documentation : Enhanced for a better user experience, making it easier for users to get started.